Open Access

ARTICLE

Attention Driven YOLOv5 Network for Enhanced Landslide Detection Using Satellite Imagery of Complex Terrain

Naveen Chandra¹, Himadri Vaidya^2,3, Suraj Sawant⁴, Shilpa Gite^5,6, Biswajeet Pradhan^7,*

1 Wadia Institute of Himalayan Geology, Dehradun, 248001, India
2 Graphic Era Hill University, Dehradun, 248001, India
3 Graphic Era Deemed University, Dehradun, 248001, India
4 COEP Technological University, Pune, 411005, India
5 Artificial Intelligence and Machine Learning Department, Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune, 412115, India
6 Symbiosis Centre of Applied AI (SCAAI), Symbiosis International (Deemed) University, Pune, 412115, India
7 Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), School of Civil and Environmental Engineering, University of Technology Sydney, Ultimo, NSW 2007, Australia

* Corresponding Author: Biswajeet Pradhan. Email:

(This article belongs to the Special Issue: Emerging Frontiers and Disruptive Technologies in Computer Science Engineering: Advancements in AI, Machine Learning, and Large Language Models to Shape Intelligent Systems)

Computer Modeling in Engineering & Sciences 2025, 143(3), 3351-3375. https://doi.org/10.32604/cmes.2025.064395

Received 14 February 2025; Accepted 27 May 2025; Issue published 30 June 2025

Abstract

Landslide hazard detection is a prevalent problem in remote sensing studies, particularly with the technological advancement of computer vision. With the continuous and exceptional growth of the computational environment, the manual and partially automated procedure of landslide detection from remotely sensed images has shifted toward automatic methods with deep learning. Furthermore, attention models, driven by human visual procedures, have become vital in natural hazard-related studies. Hence, this paper proposes an enhanced YOLOv5 (You Only Look Once version 5) network for improved satellite-based landslide detection, embedded with two popular attention modules: CBAM (Convolutional Block Attention Module) and ECA (Efficient Channel Attention). These attention mechanisms are incorporated into the backbone and neck of the YOLOv5 architecture, distinctly, and evaluated across three YOLOv5 variants: nano (n), small (s), and medium (m). The experiments use open-source satellite images from three distinct regions with complex terrain. The standard metrics, including F-score, precision, recall, and mean average precision (mAP), are computed for quantitative assessment. The YOLOv5n + CBAM demonstrates the most optimal results with an F-score of 77.2%, confirming its effectiveness. The suggested attention-driven architecture augments detection accuracy, supporting post-landslide event assessment and recovery.

---

Keywords

---